thek0tyara/llama-cpp-turboquant
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 6

lora: make sure model keep track of associated adapters (#18490)

Browse source 
* lora: make sure model keep track of associated adapters

* deprecate llama_adapter_lora_free

* minor : std::unordered_set over std::set

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Xuan-Son Nguyen 2026-01-15 10:24:28 +01:00 • committed by GitHub
parent 2a13180100
commit a7e6ddb8bd
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
7 changed files with 24 additions and 22 deletions
Download patch file Download diff file Expand all files Collapse all files

6
src/llama-model.cpp
View file

@ -468,7 +468,11 @@ llama_model::llama_model(const llama_model_params & params) : params(params), pi
pimpl->has_tensor_overrides = params.tensor_buft_overrides && params.tensor_buft_overrides[0].pattern;
}
llama_model::~llama_model() = default;
llama_model::~llama_model() {
for (auto * lora : loras) {
delete lora;
}
}
void llama_model::load_stats(llama_model_loader & ml) {
pimpl->n_elements = ml.n_elements;